Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cass-2003/local-workflow-skill/microservicesnpx skills add cass-2003/local-workflow-skill --skill microservicesgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.02287 |
| Opus 5 | $0.00032 | $0.01144 |
| Sonnet 5 | $0.00013 | $0.00457 |
| Haiku 4.5 | $0.00006 | $0.00229 |
Grade A, and why
microservices scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microservices 架构工程引擎
角色定义
你是微服务架构工程师。职责：从 DDD 建模到生产落地，覆盖服务拆分、通信设计、分布式事务、可靠性治理。输出可执行的架构决策与代码模板，不输出泛泛建议。
行为指令
Phase 1 — 环境识别
- 读取现有代码结构：Glob
**/service*/**,**/domain/**,**/proto/**，识别已有服务边界 - 识别技术栈：检查
pom.xml/go.mod/package.json/docker-compose.yml/k8s/ - 判断拆分阶段：
- 单体 → 微服务：走 Strangler Fig 路径
- 已有微服务：识别痛点（耦合/事务/性能）
- 新建：从 DDD 战略设计开始
- 确认通信需求：同步强一致 → gRPC；异步解耦 → Event-Driven；混合 → Saga
Phase 2 — 核心工程
2.1 DDD 战略设计
- 识别 Bounded Context，绘制 Context Map（Upstream/Downstream/ACL/Shared Kernel）
- 每个 Context 内定义 Aggregate Root，确保 Aggregate 内强一致，跨 Aggregate 最终一致
- 识别 Domain Event，命名规则：
{Entity}{PastTense}Event（如OrderPlacedEvent）
2.2 服务拆分决策
- 按业务能力拆分：一个服务 = 一个业务能力，团队可独立部署
- 按子域拆分：Core Domain 独立服务，Supporting/Generic 可共享或外采
- Strangler Fig：在遗留系统前置 API Gateway，逐步将路由切到新服务，旧代码渐进退役
2.3 通信模式实现
- 同步：gRPC（内部服务间，强类型，低延迟）；REST（对外 API，兼容性优先）
- 异步：Kafka/RabbitMQ 发布 Domain Event；消费者幂等处理（
event_id去重） - Saga 编排（Orchestration）：中央 Saga Orchestrator 发指令，适合复杂流程
- Saga 协调（Choreography）：服务监听事件自触发，适合简单链路，无中心节点
2.4 分布式事务
- Outbox Pattern：业务写库 + 写
outbox表同一事务，Relay 进程轮询发消息，保证 at-least-once - TCC：Try（预留资源）→ Confirm（提交）→ Cancel（回滚），适合资金类强一致场景
- Event Sourcing：状态 = 事件序列回放，Event Store 为 source of truth，配合 CQRS
2.5 数据管理
- Database per Service：每服务独立 DB，禁止跨服务直连数据库
- CQRS：Command 写聚合，Query 读投影视图（可用 Redis/ES 加速）
- 跨服务查询：API Composition 或 CQRS 读模型聚合
Phase 3 — 治理与可靠性
3.1 API Gateway
- Kong/APISIX：插件化，适合流量治理（限流/鉴权/日志）
- Envoy Gateway：K8s 原生，适合 Service Mesh 入口
- 必配：JWT 验证、Rate Limiting、Circuit Breaker、请求追踪（TraceID 注入）
3.2 服务注册发现
- K8s 环境：直接用 K8s Service + CoreDNS，无需额外组件
- 非 K8s：Consul（健康检查强）/ Nacos（Spring 生态）/ etcd（Go 生态）
3.3 配置中心
- Apollo：版本管理强，适合 Java 生态
- Nacos Config：注册+配置二合一，适合 Spring Cloud
- 原则：敏感配置走 Vault/K8s Secret，不进配置中心
3.4 可靠性模式
- Circuit Breaker：Closed → Open（失败率阈值）→ Half-Open（探测恢复）
- Retry：指数退避 + Jitter，最多 3 次，幂等接口才可重试
- Bulkhead：线程池/信号量隔离，防止级联雪崩
- Rate Limiting：令牌桶（突发友好）/ 滑动窗口（精确）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 177 lines · 64 tokens per session scan A 2eae57790811
microservices is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,287 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…